{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:16:03Z","timestamp":1742645763859,"version":"3.37.3"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2023,6,12]]},"abstract":"Human activity recognition (HAR) is one of the core research themes in ubiquitous and wearable computing. With the shift to deep learning (DL) based analysis approaches, it has become possible to extract high-level features and perform classification in an end-to-end manner. Despite their promising overall capabilities, DL-based HAR may suffer from overfitting due to the notoriously small, often inadequate, amounts of labeled sample data that are available for typical HAR applications. In response to such challenges, we propose ConvBoost -- a novel, three-layer, structured model architecture and boosting framework for convolutional network based HAR. Our framework generates additional training data from three different perspectives for improved HAR, aiming to alleviate the shortness of labeled training data in the field. Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer--we develop three \"boosters\"--R-Frame, Mix-up, and C-Drop--to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively. These new conceptual layers and boosters, that are universally applicable for any kind of convolutional network, have been designed based on the characteristics of the sensor data and the concept of frame-wise HAR. In our experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, GOTOV) we demonstrate the effectiveness of our ConvBoost framework for HAR applications based on variants of convolutional networks: vanilla CNN, ConvLSTM, and Attention Models. We achieved substantial performance gains for all of them, which suggests that the proposed approach is generic and can serve as a practical solution for boosting the performance of existing ConvNet-based HAR models. This is an open-source project, and the code can be found at https:\/\/github.com\/sshao2013\/ConvBoost<\/jats:p>","DOI":"10.1145\/3596234","type":"journal-article","created":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T22:58:16Z","timestamp":1686610696000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["ConvBoost"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7028-0944","authenticated-orcid":false,"given":"Shuai","family":"Shao","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Warwick, Coventry, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1283-3806","authenticated-orcid":false,"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Warwick, Coventry, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1635-1406","authenticated-orcid":false,"given":"Bing","family":"Zhai","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, Northumbria University, Newcastle upon Tyne, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0978-2446","authenticated-orcid":false,"given":"Paolo","family":"Missier","sequence":"additional","affiliation":[{"name":"School of Computing, Newcastle University, Newcastle upon Tyne, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1243-7563","authenticated-orcid":false,"given":"Thomas","family":"Pl\u00f6tz","sequence":"additional","affiliation":[{"name":"School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"23th International conference on architecture of computing systems","author":"Avci Akin","year":"2010","unstructured":"Akin Avci, Stephan Bosch, Mihai Marin-Perianu, Raluca Marin-Perianu, and Paul Havinga. 2010. Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey. In 23th International conference on architecture of computing systems 2010. VDE, VDE, The Netherlands, 1--10."},{"key":"e_1_2_1_2_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3397323","article-title":"Adversarial multi-view networks for activity recognition","volume":"4","author":"Bai Lei","year":"2020","unstructured":"Lei Bai, Lina Yao, Xianzhi Wang, Salil S Kanhere, Bin Guo, and Zhiwen Yu. 2020. Adversarial multi-view networks for activity recognition. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 2 (2020), 1--22.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3381012","article-title":"METIER: A deep multi-task learning based activity and user recognition model using wearable sensors","volume":"4","author":"Chen Ling","year":"2020","unstructured":"Ling Chen, Yi Zhang, and Liangying Peng. 2020. METIER: A deep multi-task learning based activity and user recognition model using wearable sensors. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 1 (2020), 1--18.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"volume-title":"An introduction to bootstrap methods with applications to R","author":"Chernick Michael R","key":"e_1_2_1_5_1","unstructured":"Michael R Chernick and Robert A LaBudde. 2014. An introduction to bootstrap methods with applications to R. John Wiley & Sons."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314399"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3090076"},{"key":"e_1_2_1_8_1","volume-title":"Human gait identification from extremely low-quality videos: an enhanced classifier ensemble method. IET biometrics 3, 2","author":"Guan Yu","year":"2014","unstructured":"Yu Guan, Yunlian Sun, Chang-Tsun Li, and Massimo Tistarelli. 2014. Human gait identification from extremely low-quality videos: an enhanced classifier ensemble method. IET biometrics 3, 2 (2014), 84--93."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2013.6712749"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886562"},{"key":"e_1_2_1_11_1","volume-title":"IJCAI 2016","author":"Hammerla Nils Y","year":"2016","unstructured":"Nils Y Hammerla, Shane Halloran, and Thomas Ploetz. 2016. Deep, convolutional, and recurrent models for human activity recognition using wearables. IJCAI 2016 (2016)."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410531.3414306"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550299"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.05.006"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Lu Jiang Deyu Meng Qian Zhao Shiguang Shan and Alexander Hauptmann. 2015. Self-paced Curriculum Learning. In AAAI.","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"e_1_2_1_16_1","volume-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Machine learning 51, 2","author":"Kuncheva Ludmila I","year":"2003","unstructured":"Ludmila I Kuncheva and Christopher J Whitaker. 2003. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Machine learning 51, 2 (2003), 181--207."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411841"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493492"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410530.3414367"},{"key":"e_1_2_1_20_1","volume-title":"Deep Neural Network Ensembles against Deception: Ensemble Diversity. Accuracy and Robustness. arXiv 1908","author":"Liu L","year":"2019","unstructured":"L Liu, W Wei, KH Chow, M Loper, E Gursoy, S Truex, and Y Wu. 2019. Deep Neural Network Ensembles against Deception: Ensemble Diversity. Accuracy and Robustness. arXiv 1908 (2019)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494998"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2971763.2971764"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123046"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267242.3267287"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-020-09268-2"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Lloyd Pellatt and Daniel Roggen. 2020. CausalBatch: Solving Complexity\/Performance Tradeoffs for Deep Convolutional and LSTM Networks for Wearable Activity Recognition. In Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers (Virtual Event Mexico) (UbiComp-ISWC '20). Association for Computing Machinery New York NY USA 272--277. https:\/\/doi.org\/10.1145\/3410530.3414365","DOI":"10.1145\/3410530.3414365"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2381112"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370276"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26561-2_6"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3328932"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410530.3414346"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11030322"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448112"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1900.0019"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136817"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489106"},{"key":"e_1_2_1_39_1","volume-title":"Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al.","author":"Wortsman Mitchell","year":"2022","unstructured":"Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. arXiv preprint arXiv:2203.05482 (2022)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263--019--01198-w"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Kei Yaguchi Kazukiyo Ikarigawa Ryo Kawasaki Wataru Miyazaki Yuki Morikawa Chihiro Ito Masaki Shuzo and Eisaku Maeda. 2020. Human Activity Recognition Using Multi-Input CNN Model with FFT Spectrograms. In Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers (Virtual Event Mexico) (UbiComp-ISWC '20). Association for Computing Machinery New York NY USA 364--367. https:\/\/doi.org\/10.1145\/3410530.3414342","DOI":"10.1145\/3410530.3414342"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832806"},{"key":"e_1_2_1_43_1","unstructured":"Hang Yuan Shing Chan Andrew P. Creagh Catherine Tong David A. Clifton and Aiden Doherty. 2022. Self-supervised Learning for Human Activity Recognition Using 700 000 Person-days of Wearable Data. arXiv:2206.02909 [eess.SP]"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397325"},{"key":"e_1_2_1_45_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"volume-title":"Ensemble methods: foundations and algorithms","author":"Zhou Zhi-Hua","key":"e_1_2_1_46_1","unstructured":"Zhi-Hua Zhou. 2019. Ensemble methods: foundations and algorithms. Chapman and Hall\/CRC."}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3596234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T22:57:35Z","timestamp":1721689055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3596234"}},"subtitle":["Boosting ConvNets for Sensor-based Activity Recognition"],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,12]]}},"alternative-id":["10.1145\/3596234"],"URL":"https:\/\/doi.org\/10.1145\/3596234","relation":{},"ISSN":["2474-9567"],"issn-type":[{"type":"electronic","value":"2474-9567"}],"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}